--- AnyEvent-MP/MP.pm 2009/08/04 23:16:57 1.29 +++ AnyEvent-MP/MP.pm 2009/08/17 03:56:34 1.59 @@ -10,20 +10,44 @@ NODE # returns this node's noderef NODE $port # returns the noderef of the port + $SELF # receiving/own port id in rcv callbacks + + # initialise the node so it can send/receive messages + initialise_node; # -OR- + initialise_node "localhost:4040"; # -OR- + initialise_node "slave/", "localhost:4040" + + # ports are message endpoints + + # sending messages snd $port, type => data...; + snd $port, @msg; + snd @msg_with_first_element_being_a_port; - $SELF # receiving/own port id in rcv callbacks + # creating/using ports, the simple way + my $simple_port = port { my @msg = @_; 0 }; + + # creating/using ports, tagged message matching + my $port = port; + rcv $port, ping => sub { snd $_[0], "pong"; 0 }; + rcv $port, pong => sub { warn "pong received\n"; 0 }; + + # create a port on another node + my $port = spawn $node, $initfunc, @initdata; + + # monitoring + mon $port, $cb->(@msg) # callback is invoked on death + mon $port, $otherport # kill otherport on abnormal death + mon $port, $otherport, @msg # send message on death - rcv $port, smartmatch => $cb->($port, @msg); +=head1 CURRENT STATUS - # examples: - rcv $port2, ping => sub { snd $_[0], "pong"; 0 }; - rcv $port1, pong => sub { warn "pong received\n" }; - snd $port2, ping => $port1; - - # more, smarter, matches (_any_ is exported by this module) - rcv $port, [child_died => $pid] => sub { ... - rcv $port, [_any_, _any_, 3] => sub { .. $_[2] is 3 + AnyEvent::MP - stable API, should work + AnyEvent::MP::Intro - outdated + AnyEvent::MP::Kernel - WIP + AnyEvent::MP::Transport - mostly stable + + stay tuned. =head1 DESCRIPTION @@ -37,7 +61,7 @@ At the moment, this module family is severly broken and underdocumented, so do not use. This was uploaded mainly to reserve the CPAN namespace - -stay tuned! The basic API should be finished, however. +stay tuned! =head1 CONCEPTS @@ -47,22 +71,21 @@ A port is something you can send messages to (with the C function). -Some ports allow you to register C handlers that can match specific -messages. All C handlers will receive messages they match, messages -will not be queued. +Ports allow you to register C handlers that can match all or just +some messages. Messages will not be queued. =item port id - C -A port id is normaly the concatenation of a noderef, a hash-mark (C<#>) as +A port ID is the concatenation of a noderef, a hash-mark (C<#>) as separator, and a port name (a printable string of unspecified format). An -exception is the the node port, whose ID is identical to it's node +exception is the the node port, whose ID is identical to its node reference. =item node -A node is a single process containing at least one port - the node -port. You can send messages to node ports to find existing ports or to -create new ports, among other things. +A node is a single process containing at least one port - the node port, +which provides nodes to manage each other remotely, and to create new +ports. Nodes are either private (single-process only), slaves (connected to a master node only) or public nodes (connectable from unrelated nodes). @@ -92,7 +115,7 @@ package AnyEvent::MP; -use AnyEvent::MP::Base; +use AnyEvent::MP::Kernel; use common::sense; @@ -102,12 +125,12 @@ use base "Exporter"; -our $VERSION = '0.1'; +our $VERSION = $AnyEvent::MP::Kernel::VERSION; + our @EXPORT = qw( - NODE $NODE *SELF node_of _any_ - resolve_node - become_slave become_public - snd rcv mon kil reg psub + NODE $NODE *SELF node_of after + resolve_node initialise_node + snd rcv mon kil reg psub spawn port ); @@ -121,14 +144,103 @@ =item $thisnode = NODE / $NODE -The C function returns, and the C<$NODE> variable contains -the noderef of the local node. The value is initialised by a call -to C or C, after which all local port -identifiers become invalid. +The C function returns, and the C<$NODE> variable contains the +noderef of the local node. The value is initialised by a call to +C. + +=item $noderef = node_of $port + +Extracts and returns the noderef from a port ID or a noderef. + +=item initialise_node $noderef, $seednode, $seednode... + +=item initialise_node "slave/", $master, $master... + +Before a node can talk to other nodes on the network it has to initialise +itself - the minimum a node needs to know is it's own name, and optionally +it should know the noderefs of some other nodes in the network. + +This function initialises a node - it must be called exactly once (or +never) before calling other AnyEvent::MP functions. + +All arguments (optionally except for the first) are noderefs, which can be +either resolved or unresolved. + +The first argument will be looked up in the configuration database first +(if it is C then the current nodename will be used instead) to find +the relevant configuration profile (see L). If none is found then +the default configuration is used. The configuration supplies additional +seed/master nodes and can override the actual noderef. + +There are two types of networked nodes, public nodes and slave nodes: + +=over 4 + +=item public nodes + +For public nodes, C<$noderef> (supplied either directly to +C or indirectly via a profile or the nodename) must be a +noderef (possibly unresolved, in which case it will be resolved). + +After resolving, the node will bind itself on all endpoints and try to +connect to all additional C<$seednodes> that are specified. Seednodes are +optional and can be used to quickly bootstrap the node into an existing +network. + +=item slave nodes + +When the C<$noderef> (either as given or overriden by the config file) +is the special string C, then the node will become a slave +node. Slave nodes cannot be contacted from outside and will route most of +their traffic to the master node that they attach to. + +At least one additional noderef is required (either by specifying it +directly or because it is part of the configuration profile): The node +will try to connect to all of them and will become a slave attached to the +first node it can successfully connect to. + +Note that slave nodes cannot change their name, and consequently, their +master, so if the master goes down, the slave node will not function well +anymore until it can re-establish conenciton to its master. This makes +slave nodes unsuitable for long-term nodes or fault-tolerant networks. + +=back + +This function will block until all nodes have been resolved and, for slave +nodes, until it has successfully established a connection to a master +server. + +All the seednodes will also be specially marked to automatically retry +connecting to them infinitely. + +Example: become a public node listening on the guessed noderef, or the one +specified via C for the current node. This should be the most common +form of invocation for "daemon"-type nodes. + + initialise_node; + +Example: become a slave node to any of the the seednodes specified via +C. This form is often used for commandline clients. + + initialise_node "slave/"; + +Example: become a slave node to any of the specified master servers. This +form is also often used for commandline clients. -=item $noderef = node_of $portid + initialise_node "slave/", "master1", "192.168.13.17", "mp.example.net"; -Extracts and returns the noderef from a portid or a noderef. +Example: become a public node, and try to contact some well-known master +servers to become part of the network. + + initialise_node undef, "master1", "master2"; + +Example: become a public node listening on port C<4041>. + + initialise_node 4041; + +Example: become a public node, only visible on localhost port 4044. + + initialise_node "localhost:4044"; =item $cv = resolve_node $noderef @@ -170,16 +282,15 @@ just export C<$SELF>, all the symbols called C are exported by this module, but only C<$SELF> is currently used. -=item snd $portid, type => @data +=item snd $port, type => @data -=item snd $portid, @msg +=item snd $port, @msg Send the given message to the given port ID, which can identify either -a local or a remote port, and can be either a string or soemthignt hat -stringifies a sa port ID (such as a port object :). +a local or a remote port, and must be a port ID. While the message can be about anything, it is highly recommended to use a -string as first element (a portid, or some word that indicates a request +string as first element (a port ID, or some word that indicates a request type etc.). The message data effectively becomes read-only after a call to this @@ -192,259 +303,150 @@ that Storable can serialise and deserialise is allowed, and for the local node, anything can be passed. -=item kil $portid[, @reason] - -Kill the specified port with the given C<@reason>. - -If no C<@reason> is specified, then the port is killed "normally" (linked -ports will not be kileld, or even notified). - -Otherwise, linked ports get killed with the same reason (second form of -C, see below). - -Runtime errors while evaluating C callbacks or inside C blocks -will be reported as reason C<< die => $@ >>. - -Transport/communication errors are reported as C<< transport_error => -$message >>. - -=item $guard = mon $portid, $cb->(@reason) - -=item $guard = mon $portid, $otherport - -=item $guard = mon $portid, $otherport, @msg - -Monitor the given port and do something when the port is killed. - -In the first form, the callback is simply called with any number -of C<@reason> elements (no @reason means that the port was deleted -"normally"). Note also that I<< the callback B never die >>, so use -C if unsure. - -In the second form, the other port will be C'ed with C<@reason>, iff -a @reason was specified, i.e. on "normal" kils nothing happens, while -under all other conditions, the other port is killed with the same reason. - -In the last form, a message of the form C<@msg, @reason> will be C. - -Example: call a given callback when C<$port> is killed. - - mon $port, sub { warn "port died because of <@_>\n" }; - -Example: kill ourselves when C<$port> is killed abnormally. - - mon $port, $self; - -Example: send us a restart message another C<$port> is killed. - - mon $port, $self => "restart"; - -=cut - -sub mon { - my ($noderef, $port, $cb) = ((split /#/, shift, 2), shift); - - my $node = $NODE{$noderef} || add_node $noderef; - - #TODO: ports must not be references - if (!ref $cb or "AnyEvent::MP::Port" eq ref $cb) { - if (@_) { - # send a kill info message - my (@msg) = ($cb, @_); - $cb = sub { snd @msg, @_ }; - } else { - # simply kill other port - my $port = $cb; - $cb = sub { kil $port, @_ if @_ }; - } - } - - $node->monitor ($port, $cb); +=item $local_port = port - defined wantarray - and AnyEvent::Util::guard { $node->unmonitor ($port, $cb) } -} +Create a new local port object and returns its port ID. Initially it has +no callbacks set and will throw an error when it receives messages. -=item $guard = mon_guard $port, $ref, $ref... +=item $local_port = port { my @msg = @_ } -Monitors the given C<$port> and keeps the passed references. When the port -is killed, the references will be freed. +Creates a new local port, and returns its ID. Semantically the same as +creating a port and calling C on it. -Optionally returns a guard that will stop the monitoring. +The block will be called for every message received on the port, with the +global variable C<$SELF> set to the port ID. Runtime errors will cause the +port to be Ced. The message will be passed as-is, no extra argument +(i.e. no port ID) will be passed to the callback. -This function is useful when you create e.g. timers or other watchers and -want to free them when the port gets killed: +If you want to stop/destroy the port, simply C it: - $port->rcv (start => sub { - my $timer; $timer = mon_guard $port, AE::timer 1, 1, sub { - undef $timer if 0.9 < rand; - }); - }); + my $port = port { + my @msg = @_; + ... + kil $SELF; + }; =cut -sub mon_guard { - my ($port, @refs) = @_; +sub rcv($@); - mon $port, sub { 0 && @refs } +sub _kilme { + die "received message on port without callback"; } -=item lnk $port1, $port2 - -Link two ports. This is simply a shorthand for: - - mon $port1, $port2; - mon $port2, $port1; - -It means that if either one is killed abnormally, the other one gets -killed as well. - -=item $local_port = port - -Create a new local port object that supports message matching. - -=item $portid = port { my @msg = @_; $finished } - -Creates a "mini port", that is, a very lightweight port without any -pattern matching behind it, and returns its ID. - -The block will be called for every message received on the port. When the -callback returns a true value its job is considered "done" and the port -will be destroyed. Otherwise it will stay alive. - -The message will be passed as-is, no extra argument (i.e. no port id) will -be passed to the callback. - -If you need the local port id in the callback, this works nicely: - - my $port; $port = miniport { - snd $otherport, reply => $port; - }; - -=cut - sub port(;&) { my $id = "$UNIQ." . $ID++; my $port = "$NODE#$id"; - if (@_) { - my $cb = shift; - $PORT{$id} = sub { - local $SELF = $port; - eval { - &$cb - and kil $id; - }; - _self_die if $@; - }; - } else { - my $self = bless { - id => "$NODE#$id", - }, "AnyEvent::MP::Port"; - - $PORT_DATA{$id} = $self; - $PORT{$id} = sub { - local $SELF = $port; - - eval { - for (@{ $self->{rc0}{$_[0]} }) { - $_ && &{$_->[0]} - && undef $_; - } - - for (@{ $self->{rcv}{$_[0]} }) { - $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] - && &{$_->[0]} - && undef $_; - } - - for (@{ $self->{any} }) { - $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] - && &{$_->[0]} - && undef $_; - } - }; - _self_die if $@; - }; - } + rcv $port, shift || \&_kilme; $port } -=item reg $portid, $name - -Registers the given port under the name C<$name>. If the name already -exists it is replaced. +=item rcv $local_port, $callback->(@msg) -A port can only be registered under one well known name. +Replaces the default callback on the specified port. There is no way to +remove the default callback: use C to disable it, or better +C the port when it is no longer needed. -A port automatically becomes unregistered when it is killed. +The global C<$SELF> (exported by this module) contains C<$port> while +executing the callback. Runtime errors during callback execution will +result in the port being Ced. -=cut - -sub reg(@) { - my ($portid, $name) = @_; - - $REG{$name} = $portid; -} +The default callback received all messages not matched by a more specific +C match. -=item rcv $portid, tagstring => $callback->(@msg), ... +=item rcv $local_port, tag => $callback->(@msg_without_tag), ... -=item rcv $portid, $smartmatch => $callback->(@msg), ... +Register (or replace) callbacks to be called on messages starting with the +given tag on the given port (and return the port), or unregister it (when +C<$callback> is C<$undef> or missing). There can only be one callback +registered for each tag. -=item rcv $portid, [$smartmatch...] => $callback->(@msg), ... +The original message will be passed to the callback, after the first +element (the tag) has been removed. The callback will use the same +environment as the default callback (see above). -Register callbacks to be called on matching messages on the given port. +Example: create a port and bind receivers on it in one go. -The callback has to return a true value when its work is done, after -which is will be removed, or a false value in which case it will stay -registered. + my $port = rcv port, + msg1 => sub { ... }, + msg2 => sub { ... }, + ; -The global C<$SELF> (exported by this module) contains C<$portid> while -executing the callback. +Example: create a port, bind receivers and send it in a message elsewhere +in one go: -Runtime errors wdurign callback execution will result in the port being -Ced. + snd $otherport, reply => + rcv port, + msg1 => sub { ... }, + ... + ; -If the match is an array reference, then it will be matched against the -first elements of the message, otherwise only the first element is being -matched. +Example: temporarily register a rcv callback for a tag matching some port +(e.g. for a rpc reply) and unregister it after a message was received. -Any element in the match that is specified as C<_any_> (a function -exported by this module) matches any single element of the message. + rcv $port, $otherport => sub { + my @reply = @_; -While not required, it is highly recommended that the first matching -element is a string identifying the message. The one-string-only match is -also the most efficient match (by far). + rcv $SELF, $otherport; + }; =cut sub rcv($@) { - my ($noderef, $port) = split /#/, shift, 2; + my $port = shift; + my ($noderef, $portid) = split /#/, $port, 2; - ($NODE{$noderef} || add_node $noderef) == $NODE{""} - or Carp::croak "$noderef#$port: rcv can only be called on local ports, caught"; + $NODE{$noderef} == $NODE{""} + or Carp::croak "$port: rcv can only be called on local ports, caught"; + + while (@_) { + if (ref $_[0]) { + if (my $self = $PORT_DATA{$portid}) { + "AnyEvent::MP::Port" eq ref $self + or Carp::croak "$port: rcv can only be called on message matching ports, caught"; + + $self->[2] = shift; + } else { + my $cb = shift; + $PORT{$portid} = sub { + local $SELF = $port; + eval { &$cb }; _self_die if $@; + }; + } + } elsif (defined $_[0]) { + my $self = $PORT_DATA{$portid} ||= do { + my $self = bless [$PORT{$port} || sub { }, { }, $port], "AnyEvent::MP::Port"; + + $PORT{$portid} = sub { + local $SELF = $port; + + if (my $cb = $self->[1]{$_[0]}) { + shift; + eval { &$cb }; _self_die if $@; + } else { + &{ $self->[0] }; + } + }; - my $self = $PORT_DATA{$port} - or Carp::croak "$noderef#$port: rcv can only be called on message matching ports, caught"; + $self + }; - "AnyEvent::MP::Port" eq ref $self - or Carp::croak "$noderef#$port: rcv can only be called on message matching ports, caught"; + "AnyEvent::MP::Port" eq ref $self + or Carp::croak "$port: rcv can only be called on message matching ports, caught"; - while (@_) { - my ($match, $cb) = splice @_, 0, 2; + my ($tag, $cb) = splice @_, 0, 2; - if (!ref $match) { - push @{ $self->{rc0}{$match} }, [$cb]; - } elsif (("ARRAY" eq ref $match && !ref $match->[0])) { - my ($type, @match) = @$match; - @match - ? push @{ $self->{rcv}{$match->[0]} }, [$cb, \@match] - : push @{ $self->{rc0}{$match->[0]} }, [$cb]; - } else { - push @{ $self->{any} }, [$cb, $match]; + if (defined $cb) { + $self->[1]{$tag} = $cb; + } else { + delete $self->[1]{$tag}; + } } } + + $port } =item $closure = psub { BLOCK } @@ -485,84 +487,238 @@ } } -=back +=item $guard = mon $port, $cb->(@reason) -=head1 FUNCTIONS FOR NODES +=item $guard = mon $port, $rcvport -=over 4 +=item $guard = mon $port + +=item $guard = mon $port, $rcvport, @msg + +Monitor the given port and do something when the port is killed or +messages to it were lost, and optionally return a guard that can be used +to stop monitoring again. + +C effectively guarantees that, in the absence of hardware failures, +that after starting the monitor, either all messages sent to the port +will arrive, or the monitoring action will be invoked after possible +message loss has been detected. No messages will be lost "in between" +(after the first lost message no further messages will be received by the +port). After the monitoring action was invoked, further messages might get +delivered again. + +Note that monitoring-actions are one-shot: once released, they are removed +and will not trigger again. + +In the first form (callback), the callback is simply called with any +number of C<@reason> elements (no @reason means that the port was deleted +"normally"). Note also that I<< the callback B never die >>, so use +C if unsure. + +In the second form (another port given), the other port (C<$rcvport>) +will be C'ed with C<@reason>, iff a @reason was specified, i.e. on +"normal" kils nothing happens, while under all other conditions, the other +port is killed with the same reason. + +The third form (kill self) is the same as the second form, except that +C<$rvport> defaults to C<$SELF>. + +In the last form (message), a message of the form C<@msg, @reason> will be +C. + +As a rule of thumb, monitoring requests should always monitor a port from +a local port (or callback). The reason is that kill messages might get +lost, just like any other message. Another less obvious reason is that +even monitoring requests can get lost (for exmaple, when the connection +to the other node goes down permanently). When monitoring a port locally +these problems do not exist. + +Example: call a given callback when C<$port> is killed. + + mon $port, sub { warn "port died because of <@_>\n" }; -=item become_public $noderef +Example: kill ourselves when C<$port> is killed abnormally. -Tells the node to become a public node, i.e. reachable from other nodes. + mon $port; -The first argument is the (unresolved) node reference of the local node -(if missing then the empty string is used). +Example: send us a restart message when another C<$port> is killed. -It is quite common to not specify anything, in which case the local node -tries to listen on the default port, or to only specify a port number, in -which case AnyEvent::MP tries to guess the local addresses. + mon $port, $self => "restart"; =cut -=back +sub mon { + my ($noderef, $port) = split /#/, shift, 2; -=head1 NODE MESSAGES + my $node = $NODE{$noderef} || add_node $noderef; -Nodes understand the following messages sent to them. Many of them take -arguments called C<@reply>, which will simply be used to compose a reply -message - C<$reply[0]> is the port to reply to, C<$reply[1]> the type and -the remaining arguments are simply the message data. + my $cb = @_ ? shift : $SELF || Carp::croak 'mon: called with one argument only, but $SELF not set,'; -While other messages exist, they are not public and subject to change. + unless (ref $cb) { + if (@_) { + # send a kill info message + my (@msg) = ($cb, @_); + $cb = sub { snd @msg, @_ }; + } else { + # simply kill other port + my $port = $cb; + $cb = sub { kil $port, @_ if @_ }; + } + } -=over 4 + $node->monitor ($port, $cb); + + defined wantarray + and AnyEvent::Util::guard { $node->unmonitor ($port, $cb) } +} + +=item $guard = mon_guard $port, $ref, $ref... + +Monitors the given C<$port> and keeps the passed references. When the port +is killed, the references will be freed. + +Optionally returns a guard that will stop the monitoring. + +This function is useful when you create e.g. timers or other watchers and +want to free them when the port gets killed: + + $port->rcv (start => sub { + my $timer; $timer = mon_guard $port, AE::timer 1, 1, sub { + undef $timer if 0.9 < rand; + }); + }); =cut -=item lookup => $name, @reply +sub mon_guard { + my ($port, @refs) = @_; + + #TODO: mon-less form? + + mon $port, sub { 0 && @refs } +} + +=item kil $port[, @reason] + +Kill the specified port with the given C<@reason>. + +If no C<@reason> is specified, then the port is killed "normally" (linked +ports will not be kileld, or even notified). + +Otherwise, linked ports get killed with the same reason (second form of +C, see below). + +Runtime errors while evaluating C callbacks or inside C blocks +will be reported as reason C<< die => $@ >>. + +Transport/communication errors are reported as C<< transport_error => +$message >>. + +=cut -Replies with the port ID of the specified well-known port, or C. +=item $port = spawn $node, $initfunc[, @initdata] -=item devnull => ... +Creates a port on the node C<$node> (which can also be a port ID, in which +case it's the node where that port resides). -Generic data sink/CPU heat conversion. +The port ID of the newly created port is return immediately, and it is +permissible to immediately start sending messages or monitor the port. -=item relay => $port, @msg +After the port has been created, the init function is +called. This function must be a fully-qualified function name +(e.g. C). To specify a function in the main +program, use C<::name>. -Simply forwards the message to the given port. +If the function doesn't exist, then the node tries to C +the package, then the package above the package and so on (e.g. +C, C, C) until the function +exists or it runs out of package names. -=item eval => $string[ @reply] +The init function is then called with the newly-created port as context +object (C<$SELF>) and the C<@initdata> values as arguments. -Evaluates the given string. If C<@reply> is given, then a message of the -form C<@reply, $@, @evalres> is sent. +A common idiom is to pass your own port, monitor the spawned port, and +in the init function, monitor the original port. This two-way monitoring +ensures that both ports get cleaned up when there is a problem. -Example: crash another node. +Example: spawn a chat server port on C<$othernode>. - snd $othernode, eval => "exit"; + # this node, executed from within a port context: + my $server = spawn $othernode, "MyApp::Chat::Server::connect", $SELF; + mon $server; -=item time => @reply + # init function on C<$othernode> + sub connect { + my ($srcport) = @_; -Replies the the current node time to C<@reply>. + mon $srcport; -Example: tell the current node to send the current time to C<$myport> in a -C message. + rcv $SELF, sub { + ... + }; + } - snd $NODE, time => $myport, timereply => 1, 2; - # => snd $myport, timereply => 1, 2,